{"id":"https://openalex.org/W3107175012","doi":"https://doi.org/10.1587/transinf.2020pap0014","title":"A Data-Centric Directive-Based Framework to Accelerate Out-of-Core Stencil Computation on a GPU","display_name":"A Data-Centric Directive-Based Framework to Accelerate Out-of-Core Stencil Computation on a GPU","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3107175012","doi":"https://doi.org/10.1587/transinf.2020pap0014","mag":"3107175012"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2020pap0014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020pap0014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020PAP0014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020PAP0014/_pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085167890","display_name":"Jingcheng Shen","orcid":"https://orcid.org/0000-0002-2090-159X"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jingcheng SHEN","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090008684","display_name":"Fumihiko Ino","orcid":"https://orcid.org/0000-0002-5757-7631"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumihiko INO","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023889181","display_name":"Albert Farr\u00e9s","orcid":"https://orcid.org/0000-0002-6129-8117"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Albert FARR\u00c9S","raw_affiliation_strings":["Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066501214","display_name":"Mauricio Hanzich","orcid":"https://orcid.org/0000-0003-4460-1118"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mauricio HANZICH","raw_affiliation_strings":["Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4026,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68188063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"E103.D","issue":"12","first_page":"2421","last_page":"2434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8933395743370056},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8375663757324219},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7309674024581909},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6114717125892639},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4912402033805847},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46990129351615906},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.46270090341567993},{"id":"https://openalex.org/keywords/out-of-core-algorithm","display_name":"Out-of-core algorithm","score":0.41522926092147827},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3134819567203522},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12772026658058167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8933395743370056},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8375663757324219},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7309674024581909},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6114717125892639},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4912402033805847},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46990129351615906},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.46270090341567993},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.41522926092147827},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3134819567203522},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12772026658058167},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1587/transinf.2020pap0014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020pap0014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020PAP0014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/334394","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/334394","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:dnet:upcommonspor::4250100ecd1665a9d6110033ec787a76","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/334394","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1587/transinf.2020pap0014","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020pap0014","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020PAP0014/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2066857215","display_name":"Principles and Practice of Massively-Parallel Computing Based on Tropical Algebra","funder_award_id":"20K21794","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3107175012.pdf","grobid_xml":"https://content.openalex.org/works/W3107175012.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1510543252","https://openalex.org/W1694630945","https://openalex.org/W1987166016","https://openalex.org/W2006682606","https://openalex.org/W2039676062","https://openalex.org/W2063656563","https://openalex.org/W2083051666","https://openalex.org/W2118850909","https://openalex.org/W2127440505","https://openalex.org/W2131322274","https://openalex.org/W2141978748","https://openalex.org/W2148038801","https://openalex.org/W2160106616","https://openalex.org/W2161042056","https://openalex.org/W2234212075","https://openalex.org/W2528222261","https://openalex.org/W2549711633","https://openalex.org/W2558636714","https://openalex.org/W2563844719","https://openalex.org/W2608177516","https://openalex.org/W2623016866","https://openalex.org/W2758320287","https://openalex.org/W2767748601","https://openalex.org/W2770872090","https://openalex.org/W2782478469","https://openalex.org/W2901892999","https://openalex.org/W2902797520","https://openalex.org/W2904182860","https://openalex.org/W2912218261","https://openalex.org/W2963153849","https://openalex.org/W2970677853","https://openalex.org/W4245236049","https://openalex.org/W4246367117","https://openalex.org/W4255162882"],"related_works":["https://openalex.org/W2497986104","https://openalex.org/W2092007952","https://openalex.org/W2972070678","https://openalex.org/W2104512032","https://openalex.org/W588863486","https://openalex.org/W2020484966","https://openalex.org/W2592770666","https://openalex.org/W2757013040","https://openalex.org/W2073614689","https://openalex.org/W2795273189"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"are":[4],"highly":[5],"efficient":[6,42],"architectures":[7],"for":[8],"parallel":[9],"stencil":[10,44],"code;":[11],"however,":[12,60],"the":[13,25,56,100,130,139,151,172,188],"small":[14,183],"device":[15,104,189],"(i.e.,":[16,94],"GPU)":[17],"memory":[18],"capacity":[19],"(several":[20],"tens":[21],"of":[22,27,132],"GBs)":[23],"necessitates":[24],"use":[26],"out-of-core":[28,43,140],"computation":[29],"to":[30,39,66,80,123,137],"process":[31],"excess":[32],"data.":[33],"Great":[34],"programming":[35,49],"effort":[36],"is":[37,87,108],"needed":[38],"manually":[40],"implement":[41],"code.":[45,141],"To":[46],"relieve":[47],"such":[48,54],"burdens,":[50],"directive-based":[51],"frameworks":[52],"emerged,":[53],"as":[55,160,162,194,196],"pipelined":[57],"accelerator":[58],"(PACC);":[59],"they":[61],"usually":[62],"lack":[63],"specific":[64],"optimizations":[65,79],"reduce":[67],"data":[68,82,102,116],"transfer.":[69,117],"In":[70],"this":[71],"paper,":[72],"we":[73],"extend":[74],"PACC":[75,120],"with":[76,182],"two":[77],"data-centric":[78],"address":[81],"transfer":[83],"problems.":[84],"The":[85,106,118,176],"first":[86],"a":[88,109,147],"direct-mapping":[89],"scheme":[90,111],"that":[91,112,145,185],"eliminates":[92],"host":[93],"CPU)":[95],"buffers,":[96],"which":[97],"intermediate":[98],"between":[99],"original":[101,133],"and":[103,157,171],"buffers.":[105],"second":[107],"region-sharing":[110],"significantly":[113],"reduces":[114],"host-to-device":[115],"extended":[119],"was":[121],"applied":[122],"an":[124,197],"acoustic":[125],"wave":[126],"propagator,":[127],"automatically":[128],"extending":[129],"length":[131],"serial":[134],"code":[135,153,178],"2.3-fold":[136],"obtain":[138],"Experimental":[142],"results":[143],"revealed":[144],"on":[146,165],"Tesla":[148],"V100":[149],"GPU,":[150],"generated":[152,177],"ran":[154],"41.0,":[155],"22.1,":[156],"3.6":[158],"times":[159,193],"fast":[161,195],"implementations":[163],"based":[164],"Open":[166],"Multi-Processing":[167],"(OpenMP),":[168],"Unified":[169],"Memory,":[170],"previous":[173],"PACC,":[174],"respectively.":[175],"also":[179],"demonstrated":[180],"usefulness":[181],"datasets":[184],"fit":[186],"in":[187],"capacity,":[190],"running":[191],"1.3":[192],"in-core":[198],"implementation.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}